Shen Xiaoqi, Lin Lan, Xu Xinze, Wu Shuicai
Department of Biomedical Engineering, Faculty of Environment and Life Sciences, Beijing University of Technology, Beijing 100124, China.
Brain Sci. 2023 Feb 2;13(2):254. doi: 10.3390/brainsci13020254.
In recent years, the rapid development of artificial intelligence has promoted the widespread application of convolutional neural networks (CNNs) in neuroimaging analysis. Although three-dimensional (3D) CNNs can utilize the spatial information in 3D volumes, there are still some challenges related to high-dimensional features and potential overfitting issues. To overcome these problems, patch-based CNNs have been used, which are beneficial for model generalization. However, it is unclear how the choice of a patchwise sampling strategy affects the performance of the Alzheimer's Disease (AD) classification. To this end, the present work investigates the impact of a patchwise sampling strategy for 3D CNN based AD classification. A 3D framework cascaded by two-stage subnetworks was used for AD classification. The patch-level subnetworks learned feature representations from local image patches, and the subject-level subnetwork combined discriminative feature representations from all patch-level subnetworks to generate a classification score at the subject level. Experiments were conducted to determine the effect of patch partitioning methods, the effect of patch size, and interactions between patch size and training set size for AD classification. With the same data size and identical network structure, the 3D CNN model trained with 48 × 48 × 48 cubic image patches showed the best performance in AD classification (ACC = 89.6%). The model trained with hippocampus-centered, region of interest (ROI)-based image patches showed suboptimal performance. If the pathological features are concentrated only in some regions affected by the disease, the empirically predefined ROI patches might be the right choice. The better performance of cubic image patches compared with cuboidal image patches is likely related to the pathological distribution of AD. The image patch size and training sample size together have a complex influence on the performance of the classification. The size of the image patches should be determined based on the size of the training sample to compensate for noisy labels and the problem of the curse of dimensionality. The conclusions of the present study can serve as a reference for the researchers who wish to develop a superior 3D patch-based CNN model with an appropriate patch sampling strategy.
近年来，人工智能的快速发展推动了卷积神经网络（CNN）在神经影像分析中的广泛应用。尽管三维（3D）CNN可以利用3D体积中的空间信息，但在高维特征和潜在的过拟合问题方面仍存在一些挑战。为了克服这些问题，基于补丁的CNN被采用，这有利于模型的泛化。然而，尚不清楚逐补丁采样策略的选择如何影响阿尔茨海默病（AD）分类的性能。为此，本研究调查了基于3D CNN的AD分类中逐补丁采样策略的影响。使用由两阶段子网络级联的3D框架进行AD分类。补丁级子网络从局部图像补丁中学习特征表示，而主体级子网络将来自所有补丁级子网络的判别性特征表示组合起来，以在主体级别生成分类分数。进行实验以确定补丁划分方法的效果、补丁大小的效果以及补丁大小与训练集大小之间的相互作用对AD分类的影响。在相同的数据大小和相同的网络结构下，使用48×48×48立方图像补丁训练的3D CNN模型在AD分类中表现出最佳性能（ACC = 89.6%）。使用以海马体为中心的基于感兴趣区域（ROI）的图像补丁训练的模型表现次优。如果病理特征仅集中在疾病影响的某些区域，凭经验预定义的ROI补丁可能是正确的选择。立方图像补丁比长方体图像补丁表现更好可能与AD的病理分布有关。图像补丁大小和训练样本大小共同对分类性能产生复杂影响。应根据训练样本的大小确定图像补丁的大小，以补偿噪声标签和维度诅咒问题。本研究的结论可为希望开发具有适当补丁采样策略的 superior 3D基于补丁的CNN模型的研究人员提供参考。
